Popular MCP Servers

Provides a read-only MCP interface to the Santismm Knowledge Platform, offering tools to retrieve curated content on engineering, AI patterns, architectures, governance, and agent taxonomy with structured output in English, Spanish, and Portuguese.

Prediction-market intelligence and crypto paper trading for AI agents. Explore data across 12 venues with 38 MCP tools, including 11 keyless tools on the hosted endpoint. Compare markets, track whales and discover crypto movers. Add a CoinRithm API key for simulated spot, futures and prediction-market trading, portfolio tracking and execution exports.

Location & routing intelligence for AI agents — geocoding, truck routing, traffic, weather, and place search.

MCP server for Backblaze B2 Cloud Storage: a focused, safe 40-tool surface (17 native B2 SDK, 19 S3 data-plane, 4 analytics) for any MCP-compatible AI client, currently incubating in Backblaze-Labs

MCP-native persistent memory layer for AI agents across Claude Code, Cursor, VS Code, and OpenClaw. Powered by hybrid vector search, BM25, and cross-encoder reranking with a published 73.1% LoCoMo benchmark accuracy.

Enables fetching YouTube transcripts, searching videos, and listing channel/playlist videos via the TranscriptFetch API.

Search Vascue's public healthcare-operations documentation: AI front desk for clinics, provider-side insurance claims automation, Cliniko integration, security. Public content only.

Converts raw HTML into structured, AI-readable page maps with 97% token reduction, enabling agents to read, click, type, and navigate any web page.

Gateway connector between LLM agents and world data, providing access to financial market prices, macroeconomic indicators, and news through a bundled endpoint catalog.

Answer CTRLRun approvals from your assistant: list the agent actions waiting on a human, inspect one action's full history, and approve, deny or resolve it, plus read receipts, effects and stats. Reads answer without a credential; the three write tools refuse without one that names a person.

Voice interface for Claude Code: you talk, the agent listens, codes, and talks back while it works. Live speech-to-text with turn-taking, Grok/xAI voices with per-subagent personas, and a real-time HUD dashboard.

Policy proxy that governs what AI assistants can reach and do: it refuses forbidden tool calls before the upstream is contacted, with per-user memory and a tamper-evident audit. Stops prompt-injection exfiltration and forbidden data combinations across connectors.

One workspace for every AI coding assistant. Governance tools for API lint, diff, persistent ledger, multi-model deliberation, security audit, and test verification. Works with Claude Code, Codex, Cursor, and Gemini CLI.

Exposes NeuralVerge's full API as MCP tools for AI research, extraction, agents, and data enrichment (LinkedIn, email, phone), enabling any MCP-compatible client to call them directly.

Enables AI agents to query public astronomy catalogs via TAP, with schema discovery, bounded ADQL queries, and reproducible results including exact queries, limits, and assumptions.

Enables MCP-compatible assistants to query, analyze, and summarize Playloop playtest data such as sessions, builds, insights, funnels, crashes, feedback, and experiments through typed tools.

Transform AI-generated text into natural, human-sounding content that successfully bypasses AI detectors.

MCP server for browser automation that lets LLMs interact with web pages through structured accessibility snapshots, bypassing the need for screenshots.

A meta-MCP server that aggregates authoritative web search and browser research tools, providing a unified interface with a cost-efficient fetch ladder for web research.

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_file, redact_file and detokenize.